© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 17802
    Prev
    Next
    INDEX
    Explanations

    numbers and fractions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ubin
    -0.07
    itera
    -0.05
     trop
    -0.05
    frica
    -0.05
    ÙĪاة
    -0.05
     ì§ĢìĽIJíķ©ëĭĪëĭ¤
    -0.05
    æĪĸå°Ĩ
    -0.05
    漬
    -0.05
    ç§ij级
    -0.05
    اÛĮÛĮ
    -0.05
    POSITIVE LOGITS
    åħ¼
    0.06
    zec
    0.06
    åı¯éĢīä¸Ń
    0.06
    æľ¬æ³ķ
    0.05
    داء
    0.05
    讳
    0.05
    guas
    0.05
    ä¹ĭé£İ
    0.05
    å½ķå¾Ĺ
    0.05
     espuma
    0.05
    Activations Density 0.014%

    No Known Activations